From Accounting to Coordination: A Virtual Water-Aware Electricity-Computation-Water Nexus Framework for Data Center Dispatch
2026-05-25 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors explain that as data centers grow, they use more electricity, which causes more water to be used at power plants. Traditional methods to measure water use don't account for how power decisions change water use over time. To fix this, the authors created a new model that links water use directly to electricity management using advanced math and machine learning. They tested this on standard power system examples and showed it can reduce water use while keeping the power system working well. This helps better understand and manage water use tied to electricity for data centers.
Data centersElectricity demandWater withdrawalsPower system dispatchWater footprintDispatch optimizationDeep learningDifferentiable optimizationIEEE test systemsFreshwater conservation
Authors
Haiyang You, Chengwei Lou, Jin Zhao, Yue Zhou, Lu Zhang, Jin Yang
Abstract
The expansion of data centers (DCs) drives a sustained increase in electricity demand and associated water withdrawals at generation sites. These withdrawals occur at generation sites and are virtually allocated to demand based on network power flows. Consequently, the actual water footprint of a specific load varies dynamically with generation dispatch and network conditions. Existing approaches typically rely on static statistical accounting to quantify these water footprints. However, such static methods fail to capture how dispatch optimization and workload relocation dynamically affect water withdrawals. As a result, static statistical accounting approaches remain decoupled from the optimization process, rendering them incapable of guiding workload relocation or power dispatch to mitigate water stress. To address this limitation, this paper develops an operational electricity-computation-water (ECW) nexus framework that internalizes virtual water impacts directly into power system dispatch. The framework represents dispatch optimization as a differentiable optimization layer embedded within a deep learning architecture, enabling efficient end-to-end learning of coordination policies while preserving operational feasibility. Combined with fixed-point coordination, the framework enforces consistency between virtual water attribution and physical generation-side withdrawals. Case studies on the IEEE 30-bus and 118-bus test systems demonstrate reliable convergence, exact power-water consistency, and reductions of approximately 3-5% in generation-related freshwater withdrawals under water-constrained conditions.